Best Gemini prompts for Financial and Investment Analysts

Develop a Python script that utilizes the Google Cloud AI Platform to create a regression model for predicting stock prices based on historical market data, including economic indicators and company performance metrics. The script should incorporate data from Google Finance and Quandl, and output a set of optimized portfolio weights that minimize risk while maximizing returns. Ensure the model accounts for sector rotation and geographic diversification, and provide a statistical summary of the results, including mean absolute error and R-squared values.

Create a data validation pipeline using SQL and Tableau to audit the accuracy and completeness of ESG (Environmental, Social, and Governance) metrics for a set of publicly traded companies. The pipeline should ingest data from Bloomberg and Refinitiv, and output a report highlighting any discrepancies or inconsistencies in the data, including missing values and outliers. Develop a set of data cleaning scripts to address these issues, and provide a summary of the results, including data accuracy and query optimization metrics.

Develop a machine learning model using Google's AutoML platform to predict credit spreads for a set of corporate bonds based on historical market data, including credit ratings, yield curves, and macroeconomic indicators. The model should incorporate data from Moody's and S&P Global, and output a set of predicted credit spreads and confidence intervals. Develop a set of statistical tests to evaluate the model's performance, including mean absolute error and mean squared error, and provide a summary of the results, including model precision and query optimization metrics.

Optimize a Snowflake data warehouse to improve query performance and reduce costs for a set of complex analytics workloads, including data aggregation and filtering. Develop a set of SQL scripts to analyze query patterns and identify bottlenecks, and provide a report highlighting opportunities for optimization, including data pruning, indexing, and caching. Develop a set of recommendations for optimizing data storage and compute resources, and provide a summary of the results, including data accuracy and query optimization metrics.